Kush Choudhary searchformyusername

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

Must be one of the following:

feat: A new feature. fix: A bug fix. docs: Documentation only changes. style: Changes that do not affect the meaning of the code (white-space, formatting, missing semi-colons, etc). refactor: A code change that neither fixes a bug nor adds a feature. perf: A code change that improves performance. test: Adding missing tests. chore: Changes to the build process or auxiliary tools and libraries such as documentation generation.

Chat GPT "DAN" (and other "Jailbreaks")

Frameworks

Semantic UI: Semantic empowers designers and developers by creating a shared vocabulary for UI
Bootstrap: Bootstrap is a free and open-source CSS framework directed at responsive, mobile-first front-end web development. It contains CSS- and JavaScript-based design templates for typography, forms, buttons, navigation, and other interface components
Material-UI: React components for faster and easier web development. Build your own design system, or start with Material Design

Illustrators

unDraw: Open-source illustrations for any idea you can imagine and create.
paid Iconscout: Get high-quality Icons, Illustrations and Stock photos at one place

Icons

npx create-react-app myapp

// Import the React and ReactDOM libraries
// Create a react component
// Take the react component and show it on the screen

- setting states in Class based component is done by simply `state = { var1: [], var2: 'value' }`

	rules:
	- id: env-set
	patterns:
	- pattern-either:
	- pattern: \|
	subprocess.check_output([..., "=~/env\|set/", ...])
	- pattern: \|
	subprocess.run([..., "=~/env\|set/", ...])
	- pattern: \|
	subprocess.Popen([..., "=~/env\|set/", ...])

	# Copyright 2017-2020 Jeff Foley. All rights reserved.
	# Use of this source code is governed by Apache 2 LICENSE that can be found in the LICENSE file.

	# Should results only be collected passively and without DNS resolution? Not recommended.
	#mode = passive
	mode = active

	# The directory that stores the Cayley graph database and other output files
	# The default for Linux systems is: $HOME/.config/amass
	#output_directory = amass

	#!/bin/bash

	# Written by Frans Rosén (twitter.com/fransrosen)
	_debug="$2" #turn on debug
	_timeout="20"
	#you need a valid key, since the errors happens after it validates that the key exist. we do not need the secret key, only access key
	_aws_key="AKIA..."
	H_ACCEPT="accept-language: en-US,en;q=0.9,sv;q=0.8,zh-TW;q=0.7,zh;q=0.6,fi;q=0.5,it;q=0.4,de;q=0.3"
	H_AGENT="user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36"

	" plugins
	let need_to_install_plugins = 0
	if empty(glob('~/.vim/autoload/plug.vim'))
	silent !curl -fLo ~/.vim/autoload/plug.vim --create-dirs
	\ https://raw.githubusercontent.com/junegunn/vim-plug/master/plug.vim
	let need_to_install_plugins = 1
	endif

	call plug#begin()
	Plug 'tpope/vim-sensible'